I am currently a 3rd year (2021-) Ph.D. student at Medical Mechatronics Lab of the Department of Electronic Engineering, The Chinese University of Hong Kong, supervised by Prof. Hongliang Ren. I am honored to have Previously, I was an Embedded Software Engineer at Continental Automotive in Singapore. Before that, I worked with Prof. Chengkuo Lee in the Department of Electrical and Computer Engineering, National University of Singapore and received my M.Sc. degree in 2019. From 2014 to 2018, I studied at Soochow University and received B.Eng. degree in Information Engineering.

My research interests include resource-efficient medical image analysis and intelligent robotic surgery, specifically,

• data/label-efficient learning;
• domain adaptation/generalization, robustness;
• efficient adaptation of foundation/large models;
• etc.

I am always open to discussions and collaborations, so please don’t hesitate to contact me via email if you have any inquiries or would like to explore potential collaborative opportunities.

🔥 News

• 2023.08: Our paper “SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation” has been accepted as an Oral Presentation at the MedAGI workshop, MICCAI 2023.
• 2023.06: Our paper “Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis” is accepted by IROS-2023.
• 2023.06: One paper about robust medical image segmentation is accepted by IEEE Transactions on Automation Science and Engineering.
• 2023.05: One paper about annotation-efficient polyp segmentation was early accepted by MICCAI-2023.
• 2022.06: One paper about synthetic data generation from limited sources is accepted by MICCAI-2022.

📝 Publications

*: First author; **: Corresponding author

Full publications.

Foundation Model

MedAGI Workshop

SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation

An Wang*, Mobarakol Islam*, Mengya Xu, Yang Zhang, and Hongliang Ren**

Oral, MICCAI 2023 1st International Workshop on Foundation Models for General Medical AI.

arXiv

Annotation-efficient Learning

MICCAI-2023

S$^2$ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation

An Wang*, Mengya Xu, Yang Zhang, Mobarakol Islam, and Hongliang Ren**

MICCAI-2023 Early Accepted (Top 14% among 2253 submissions).

arXiv | code

Synthetic Data Generation and Learning

IROS-2023

Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis

An Wang*, Mobarakol Islam*, Mengya Xu, and Hongliang Ren**

IROS-2023

arXiv | code

MICCAI-2022

Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You Need

An Wang*, Mobarakol Islam*, Mengya Xu, and Hongliang Ren**

MICCAI-2022

arXiv | Springer | code

Domain Adaptation/Generalization

IEEE T-ASE

Curriculum-Based Augmented Fourier Domain Adaption for Robust Medical Image Segmentation

An Wang*, Mobarakol Islam*, Mengya Xu*, and Hongliang Ren**

IEEE Transactions on Automation Science and Engineering (T-ASE) 2023

arXiv | IEEE | code

📖 Educations

• 2021.10 - now, Ph.D., Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
• 2018.08 - 2019.06, M.Sc., Electrical Engineering, National University of Singapore, Singapore
• 2014.09 - 2018.06, B.Eng., Information Engineering, Soochow University, Suzhou, China

💻 Teaching

• Intelligent Wearable Electronics, Teaching Assistant; 2023.01 - 2023.05
• Probability for Engineers, Teaching Assistant; 2021.09 - 2021.12, 2022.09 - 2022.12, 2023.09 - 2023.12
• Robotic Perception and Intelligence, Teaching Assistant, 2022.01 - 2022.05